AMD Radeon RX 6950 XT vs NVIDIA GeForce RTX 5090 D v2 Full Specs

Summary

5,120 Shaders 2.32GHz	21,760 Shaders 2.41GHz
16GB GDDR6576GB/s	24GB GDDR71.34TB/s
Peak·FP32·FP16 23.8 TFLOPS	Peak·FP32·FP16 104.8 TFLOPS
Form Factor PCIe Card	Form Factor PCIe Card
TDP 335W	TDP 575W
Power Connectors - 2x 8-Pin	Power Connectors 1x 16-Pin 12VHPWR -

Highlights

Peak OPS

Peak OPS FP32 FP16 Tensor FP4 FP4 Tensor Sparse Tensor FP8-16 FP8-16 Tensor Sparse Tensor FP8-32 FP8-32 Tensor Sparse Tensor FP16-16 FP16-16 Tensor Sparse Tensor FP16-32 FP16-32 Tensor Sparse FP64 BF16 Tensor BF16 BF16 Tensor Sparse Tensor TF32 Tensor INT8 Memory Bandwidth TDP

Radeon RX 6950 XT47.6 TFLOPSFP16

x1

GeForce RTX 5090 D v22.38 PFLOPSFP4 Tensor Sparse

x49.90

Show Top Score

Theoretical Performance

Clock Speed2324MHz UC·Base·Boost·OC	Clock Speed2407MHz UC·Base·Boost·OC
Peak OPS 47.6 TFLOPSFP16	Peak OPS 2.38 PFLOPSFP4 Tensor Sparse
-	Tensor FP4 1.19 PFLOPS FP4 Tensor Sparse 2.38 PFLOPS
-	Tensor FP8-16 593.8 TFLOPS FP8-16 Tensor Sparse 1.19 PFLOPS Tensor FP8-32 296.9 TFLOPS FP8-32 Tensor Sparse 593.8 TFLOPS
-	Tensor FP16-16 296.9 TFLOPS FP16-16 Tensor Sparse 593.8 TFLOPS Tensor FP16-32 148.4 TFLOPS FP16-32 Tensor Sparse 296.9 TFLOPS
-	BF16 104.8 TFLOPS Tensor BF16 148.4 TFLOPS BF16 Tensor Sparse 296.9 TFLOPS
Tensor TF32 -	Tensor TF32 74.22 TFLOPS
FP32 23.8 TFLOPS	FP32 104.8 TFLOPS
FP64 1.49 TFLOPS	FP64 1.64 TFLOPS
-	Tensor INT8 593.8 TOPS
Ray -	Ray 317.7 TOPS
Pixel Rate 297.5 GPixel/s	Pixel Rate 423.6 GPixel/s
Texture Rate 743.7 GTexel/s	Texture Rate 1.64 TTexel/s

Core Config

Shaders 5,120 Shaders	Shaders 21,760 Shaders
TMUs 320 TMUs	TMUs 680 TMUs
ROPs 128 ROPs	ROPs 176 ROPs
Tensor Cores -	Tensor Cores 510 T-Cores
RT Cores 80 RT-Cores	RT Cores 170 RT-Cores
CUs 80 CUs	SMs 170 SMs

Clocks

Base Clock 1.93GHz	Base Clock 2.01GHz
Boost Clock 2.32GHz	Boost Clock 2.41GHz
Tensor Clock -	Tensor Clock 2.27GHz

Cache

L2 Cache 4.1MB shared	L2 Cache 98.3MB shared
L3 Cache 128MB shared	L3 Cache -
L3 Bandwidth 1.66TB/s	L3 Bandwidth -

Memory

16GB GDDR6	24GB GDDR7
Memory Bus 256-bit	Memory Bus 384-bit
Memory Speed 18GT/s	Memory Speed 28GT/s
Memory Bandwidth 576GB/s	Memory Bandwidth 1.34TB/s

Power & Thermals

TDP 335W	TDP 575W
Max Temp 110°C Max	Max Temp 90°C Max

Video Output

Multi-Monitor 4	Multi-Monitor 4
HDCP HDCP 2.3	HDCP HDCP 2.3

Ports

-	3x DisplayPort 2.1
2x DisplayPort 1.4	-
1x HDMI 2.1	1x HDMI 2.1
1x USB-C	-

Encoder

Encoder Model VCN 3.0

Encoder Model 3x NVENC 9

Decoder

Decoder Model VCN 3.0

Decoder Model 2x NVDEC 6

Card

Form Factor PCIe Card	Form Factor PCIe Card
PCIe 2.5-Slots	PCIe 2.1-Slots
Height 120 mm (4.72") Width 267 mm (10.51") Depth 50 mm (1.97")	Height 137 mm (5.39") Width 304 mm (11.97") Depth 42 mm (1.65")
Cooling Open-Air 3x Fans	Cooling Open-Air 2x Fans
Power Connectors 2x 8-Pin	Power Connectors 1x 16-Pin 12VHPWR

Chip

Manufacturer AMD	Manufacturer NVIDIA
Chip Designer AMD	Chip Designer NVIDIA
Architecture RDNA 2	Architecture Blackwell
Family Radeon RX 6000	Family GeForce 50
Branding	Branding
Codename Sienna Cichlid	Codename NV192
Chip Variant Navi 21 XL	Chip Variant GB202-250-A1
Market Segment Desktop	Market Segment Desktop
Release Date May 10, 2022	Release Date Jan 6, 2025

Fabrication

Foundry TSMC	Foundry TSMC
Fabrication Node N7	Fabrication Node 4NP
Die Size 520mm²	Die Size 762mm²
Transistor Count 26.8 Billion	Transistor Count 92.2 Billion
Transistor Density 51.56 MTr/mm²	Transistor Density 121.1 MTr/mm²

Images

No images available

No images available

Competitors

AMDRadeon RX 6950 XT vs GPU NVIDIAGeForce RTX 5080 AMDRadeon RX 6950 XT vs GPU AMDRadeon RX 9070 XT AMDRadeon RX 6950 XT vs GPU NVIDIAGeForce RTX 5090 Show 12 more

NVIDIAGeForce RTX 5090 D v2 vs GPU NVIDIAGeForce RTX 5090 D NVIDIAGeForce RTX 5090 D v2 vs GPU NVIDIAGeForce RTX 5090 NVIDIAGeForce RTX 5090 D v2 vs GPU NVIDIARTX PRO 6000 Blackwell Show 12 more